Turn the current interactive conversation into an owner-reviewed reusable Agentlas agent; accept JSON or JSONL only for explicit terminal and automation runs.
74%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./claude/plugins/agentlas-core-engine-meta-agent/runtime-support/skills/session-agent-builder/SKILL.mdThe canonical home for this skill is session-agent-builder in agentlas-ai/Agentlas-OS
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The interactive route ingests the visible turns of the current conversation, which can include outsider-authored web or tool content the agent previously fetched or searched, but no outsider can post into this conversation on their own, so the exposure is agent-selected rather than forced delivery.
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.